JPEG Artifacts Reduction via Deep Convolutional Sparse Coding

To effectively reduce JPEG compression artifacts, we propose a deep convolutional sparse coding (DCSC) network architecture. We design our DCSC in the framework of classic learned iterative shrinkage-threshold algorithm. To focus on recognizing and separating artifacts only, we sparsely code the fea...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings / IEEE International Conference on Computer Vision pp. 2501 - 2510
Main Authors: Fu, Xueyang, Zha, Zheng-Jun, Wu, Feng, Ding, Xinghao, Paisley, John
Format: Conference Proceeding
Language:English
Published: IEEE 01.10.2019
Subjects:
Convolution
Convolutional codes
Encoding
Feature extraction
Image coding
Task analysis
Transform coding
ISSN:2380-7504
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract To effectively reduce JPEG compression artifacts, we propose a deep convolutional sparse coding (DCSC) network architecture. We design our DCSC in the framework of classic learned iterative shrinkage-threshold algorithm. To focus on recognizing and separating artifacts only, we sparsely code the feature maps instead of the raw image. The final de-blocked image is directly reconstructed from the coded features. We use dilated convolution to extract multi-scale image features, which allows our single model to simultaneously handle multiple JPEG compression levels. Since our method integrates model-based convolutional sparse coding with a learning-based deep neural network, the entire network structure is compact and more explainable. The resulting lightweight model generates comparable or better de-blocking results when compared with state-of-the-art methods.
AbstractList To effectively reduce JPEG compression artifacts, we propose a deep convolutional sparse coding (DCSC) network architecture. We design our DCSC in the framework of classic learned iterative shrinkage-threshold algorithm. To focus on recognizing and separating artifacts only, we sparsely code the feature maps instead of the raw image. The final de-blocked image is directly reconstructed from the coded features. We use dilated convolution to extract multi-scale image features, which allows our single model to simultaneously handle multiple JPEG compression levels. Since our method integrates model-based convolutional sparse coding with a learning-based deep neural network, the entire network structure is compact and more explainable. The resulting lightweight model generates comparable or better de-blocking results when compared with state-of-the-art methods.
Author Wu, Feng
Fu, Xueyang
Zha, Zheng-Jun
Paisley, John
Ding, Xinghao
Author_xml – sequence: 1
  givenname: Xueyang
  surname: Fu
  fullname: Fu, Xueyang
  organization: University of Science and Technology of China
– sequence: 2
  givenname: Zheng-Jun
  surname: Zha
  fullname: Zha, Zheng-Jun
  organization: University of Science and Technology of China
– sequence: 3
  givenname: Feng
  surname: Wu
  fullname: Wu, Feng
  organization: University of Science and Technology of China
– sequence: 4
  givenname: Xinghao
  surname: Ding
  fullname: Ding, Xinghao
  organization: Xiamen University
– sequence: 5
  givenname: John
  surname: Paisley
  fullname: Paisley, John
  organization: Columbia University
BookMark eNotzL1OwzAUQGGDQKItnRlY_AIJ13ZiXw8MVSilqBKIv7W6dWxkFJwoSSvx9oBgOtI3nCk7SW3yjF0IyIUAe7WuqrdcgrA5gCztEZtbg8JIFAWCwmM2kQohMyUUZ2w6DB8AykrUE3Z9_7hc8UU_xkBuHPiTr_dujG3ih0j8xvuOV206tM3-F6nhzx31g__BOqb3c3YaqBn8_L8z9nq7fKnuss3Dal0tNlmU2o5ZcITamVCbnQOrjdMQVLBQagUUnAuEBEQlBe3QeIkQtKqLsjZqR0GRmrHLv2_03m-7Pn5S_7W1AIgg1DcawkpW
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICCV.2019.00259
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library (IEL) (UW System Shared)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 9781728148038
1728148030
EISSN 2380-7504
EndPage 2510
ExternalDocumentID 9008801
Genre orig-research
GroupedDBID 29O
6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IPLJI
M43
OCL
RIE
RIL
RIO
RNS
ID FETCH-LOGICAL-i269t-fca86c7fd7bc0967c60f3f905630afccfa8a0aa5af6c87e280f63d45d73baf3a3
IEDL.DBID RIE
ISICitedReferencesCount 103
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000531438102064&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:38:47 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i269t-fca86c7fd7bc0967c60f3f905630afccfa8a0aa5af6c87e280f63d45d73baf3a3
PageCount 10
ParticipantIDs ieee_primary_9008801
PublicationCentury 2000
PublicationDate 2019-10-01
PublicationDateYYYYMMDD 2019-10-01
PublicationDate_xml – month: 10
  year: 2019
  text: 2019-10-01
  day: 01
PublicationDecade 2010
PublicationTitle Proceedings / IEEE International Conference on Computer Vision
PublicationTitleAbbrev ICCV
PublicationYear 2019
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0039286
Score 2.4968584
Snippet To effectively reduce JPEG compression artifacts, we propose a deep convolutional sparse coding (DCSC) network architecture. We design our DCSC in the...
SourceID ieee
SourceType Publisher
StartPage 2501
SubjectTerms Convolution
Convolutional codes
Encoding
Feature extraction
Image coding
Task analysis
Transform coding
Title JPEG Artifacts Reduction via Deep Convolutional Sparse Coding
URI https://ieeexplore.ieee.org/document/9008801
WOSCitedRecordID wos000531438102064&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JT0IxEJ4g8eAJFYx7evDok8dbuhw8GASXAyFu4Uam0zYhMUDgwe-3fTzRgxdvTQ9t8nWZmXa-bwCuSPGcSPvzzWPyAQpipLk1kcJEOI5KO6nLYhNiMJCjkRrW4HrLhbHWlsln9iY0y798M6NVeCprK2-wZCBr7QjBN1yt71vXm3nJK-meTqzaT93uR0jcCmqUSRAi_VU7pTQd_cb_Jt2H1g8Hjw231uUAanZ6CI3KaWTVkVw24fZ52Htgd34DBI7Ckr0ELdaANltPkN1bO2d-xHW1w_CTvc59LGt9Zxi3Be_93lv3MapqIkSThKsicoSSk3BGaPLRhyAeu9SpOMh8oSNyKNEDnqPjJIVNZOx4arLciFSjSzE9gvp0NrXHwJzOQ16hd8gym2FHYmYMplxqR94tzNwJNAMa4_lG9mJcAXH6d_cZ7AW4N3lu51AvFit7Abu0LibLxWW5Vl_0FJdM
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4QNNETKhjx2YNHV5bdbh8HDwZBUCRE0XAj026bkBggvH6_7bKiBy_emh7a5OtjZtr5vgG41pIlWit3vlmoXYCCGChm0kBixC1DqaxQWbEJ3uuJ4VD2C3Cz5cIYY7LkM3Prm9lffjrVK_9UVpPOYAlP1tpJKI3CDVvr-951hl6wXLynHspap9H48KlbXo8y8lKkv6qnZMajVfrftAdQ-WHhkf7WvhxCwUyOoJS7jSQ_lIsy3D31m4_k3m0Bz1JYkFevxurxJusxkgdjZsSNuM73GH6St5mLZo3r9ONW4L3VHDTaQV4VIRhHTC4Dq1EwzW3KlXbxB9cstLGVoRf6Qqu1RYEO8gQt04KbSISWxSlNUh4rtDHGx1CcTCfmBIhVic8sdC4ZNRTrAmmaYsyEsto5htRWoezRGM02whejHIjTv7uvYK89eOmOup3e8xnse-g3WW_nUFzOV-YCdvV6OV7ML7N1-wIDR5qT
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+%2F+IEEE+International+Conference+on+Computer+Vision&rft.atitle=JPEG+Artifacts+Reduction+via+Deep+Convolutional+Sparse+Coding&rft.au=Fu%2C+Xueyang&rft.au=Zha%2C+Zheng-Jun&rft.au=Wu%2C+Feng&rft.au=Ding%2C+Xinghao&rft.date=2019-10-01&rft.pub=IEEE&rft.eissn=2380-7504&rft.spage=2501&rft.epage=2510&rft_id=info:doi/10.1109%2FICCV.2019.00259&rft.externalDocID=9008801